tabnet: Fit 'TabNet' Models for Classification and Regression

Implements the 'TabNet' model by Sercan O. Arik et al. (2019) <doi:10.48550/arXiv.1908.07442> with 'Coherent Hierarchical Multi-label Classification Networks' by Giunchiglia et al. <doi:10.48550/arXiv.2010.10151> and provides a consistent interface for fitting and creating predictions. It's also fully compatible with the 'tidymodels' ecosystem.

Version: 0.7.0
Depends: R (≥ 3.6)
Imports: coro, data.tree, dials, dplyr, ggplot2, hardhat (≥ 1.3.0), magrittr, Matrix, methods, parsnip, progress, purrr, rlang, stats, stringr, tibble, tidyr, torch (≥ 0.4.0), tune, utils, vctrs, withr, zeallot
Suggests: cli, knitr, modeldata, patchwork, recipes, rmarkdown, rsample, spelling, testthat (≥ 3.0.0), tidymodels, tidyverse, vip, visdat, workflows, yardstick
Published: 2025-04-17
DOI: 10.32614/CRAN.package.tabnet
Author: Daniel Falbel [aut], RStudio [cph], Christophe Regouby [cre, ctb], Egill Fridgeirsson [ctb], Philipp Haarmeyer [ctb], Sven Verweij ORCID iD [ctb]
Maintainer: Christophe Regouby <christophe.regouby at free.fr>
BugReports: https://github.com/mlverse/tabnet/issues
License: MIT + file LICENSE
URL: https://mlverse.github.io/tabnet/, https://github.com/mlverse/tabnet
NeedsCompilation: no
Language: en-US
Materials: README NEWS
CRAN checks: tabnet results

Documentation:

Reference manual: tabnet.pdf
Vignettes: Hierarchical Classification (source, R code)
Training a Tabnet model from missing-values dataset (source, R code)
Interpretation tools (source, R code)
Self-supervised training and fine-tuning (source, R code)
Fitting tabnet with tidymodels (source, R code)

Downloads:

Package source: tabnet_0.7.0.tar.gz
Windows binaries: r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries: r-release (arm64): tabnet_0.7.0.tgz, r-oldrel (arm64): tabnet_0.7.0.tgz, r-release (x86_64): tabnet_0.7.0.tgz, r-oldrel (x86_64): tabnet_0.7.0.tgz
Old sources: tabnet archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=tabnet to link to this page.